<![CDATA[Rice distribution stability plays a strategic role in ensuring urban food security, particularly in metropolitan regions such as Jakarta where supply-demand dynamics are highly complex. This study aims to develop an integrated clustering-based decision support framework to classify regional rice distribution conditions and enhance adaptive allocation strategies. Monthly rice availability and demand data from 2021–2023 across seven administrative regions in Jakarta were analyzed using the K-Means clustering algorithm. Optimal cluster determination employed the Elbow and Silhouette methods. Cluster validation was conducted using Silhouette, Davies–Bouldin, and Calinski–Harabasz indices. A comparative analysis with Hierarchical Clustering (Ward linkage) was also performed. The clustering results were integrated into a Business Intelligence dashboard. Three optimal clusters were identified, representing high-surplus, moderate-surplus, and deficit conditions. K-Means demonstrated superior cluster compactness and separation quality compared to Hierarchical Clustering, with a Silhouette score of 0.62 and a Davies–Bouldin index of 0.41. The proposed framework improves operational transparency and supports evidence-based redistribution policies. This approach also contributes to strengthening adaptive food security management in metropolitan areas.]]>
Copyrights © 2026
